Staff AI Application Engineer - Heterogeneous Computing

As a Staff AI Application Engineer on Axelera AI’s Model Enablement team, you will build the platform that helps engineers bring models onto the company’s Metis and Europa AI accelerators. The work spans model capture and graph partitioning, compiler and runtime integration, heterogeneous execution across accelerators and host CPUs, and performance tuning across complete application pipelines. You will also develop hardware-enabled tools and verification workflows that engineers and AI coding agents can use to iterate and validate changes.

The role calls for substantial systems engineering experience, including system-level design ownership and hands-on work with heterogeneous computing. You will collaborate with compiler, runtime and application teams, and turn lessons from important customer models into reusable platform improvements. Axelera AI allows fully remote work from European countries, including the UK.

Highlights

• Build model ingestion, partitioning and execution capabilities across AI accelerators and host hardware.
• Improve end-to-end performance through profiling, scheduling, batching and data-movement optimizations.
• Develop reusable bring-up tools, hardware environments and CI verification workflows.
• Work remotely from a European country or from listed offices, including Florence and Milan.